metadata
license: apache-2.0
metrics:
- accuracy
- f1
Returns age bin based on a facial image.
See https://www.kaggle.com/code/dima806/facial-age-years-detection-vit for more details.
Classification report:
precision recall f1-score support
01 0.6966 0.9236 0.7942 445
02 0.4165 0.6000 0.4917 445
03 0.7338 0.2539 0.3773 445
04 0.8916 0.1663 0.2803 445
05 0.5503 0.9730 0.7030 444
06-07 0.7855 0.6090 0.6861 445
08-09 0.6561 0.7933 0.7182 445
10-12 0.7358 0.7011 0.7181 445
13-15 0.7949 0.7663 0.7803 445
16-20 0.6468 0.7342 0.6878 444
21-25 0.6507 0.6126 0.6311 444
26-30 0.4203 0.5865 0.4897 445
31-35 0.5272 0.2180 0.3084 445
36-40 0.4751 0.3865 0.4263 445
41-45 0.5074 0.6966 0.5871 445
46-50 0.4792 0.5968 0.5316 444
51-55 0.5321 0.5034 0.5173 445
56-60 0.5359 0.4022 0.4596 445
61-65 0.7442 0.2157 0.3345 445
66-70 0.4760 0.8022 0.5975 445
71-80 0.8077 0.7079 0.7545 445
81-90 0.8478 0.9888 0.9129 445
90+ 0.9978 1.0000 0.9989 445
accuracy 0.6190 10231
macro avg 0.6482 0.6190 0.5994 10231
weighted avg 0.6483 0.6190 0.5994 10231